基于病灶自动识别与自动分割技术的胃癌人工智能影像辅助诊断系统的开发与应用

注册号:

Registration number:

ChiCTR2500112205 

最近更新日期:

Date of Last Refreshed on:

2025-11-11 15:35:17 

注册时间:

Date of Registration:

2025-11-11 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于病灶自动识别与自动分割技术的胃癌人工智能影像辅助诊断系统的开发与应用

Public title:

Development and Application of an Artificial Intelligence–Based Imaging-Assisted Diagnostic System for Gastric Cancer Using Automatic Lesion Detection and Segmentation Technology

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于病灶自动识别与自动分割技术的胃癌人工智能影像辅助诊断系统的开发与应用

Scientific title:

Development and Application of an Artificial Intelligence–Based Imaging-Assisted Diagnostic System for Gastric Cancer Using Automatic Lesion Detection and Segmentation Technology

研究课题代号(代码):

Study subject ID:

在二级注册机构或其它机构的注册号:

The registration number of the Partner Registry or other register:

申请注册联系人:

王胤奎 

研究负责人:

李子禹 

Applicant:

yinkui wang 

Study leader:

Ziyu Li 

申请注册联系人电话:

Applicant telephone:

+86 151 2007 9156

研究负责人电话:

Study leader's
telephone:

+86 10 8819 6605

申请注册联系人传真 :

Applicant Fax:

研究负责人传真:

Study leader's fax:

申请注册联系人电子邮件:

Applicant E-mail:

wykchangfeng@pku.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

ligregory@outlook.com

申请单位网址(自愿提供):

Applicant website(voluntary supply):

研究负责人网址(自愿提供):

Study leader's website(voluntary supply):

申请注册联系人通讯地址:

北京海淀区阜成路52号北京大学肿瘤医院西侧楼16层胃肠肿瘤中心一病区

研究负责人通讯地址:

北京海淀区阜成路52号

Applicant address:

Gastrointestinal Cancer Center, Peking University Cancer Hospital & Institute, Haidian District, 52

Study leader's address:

52 Fucheng Road Haidian District Beijing

申请注册联系人邮政编码:

Applicant postcode:

研究负责人邮政编码:

Study leader's postcode:

申请人所在单位:

北京大学肿瘤医院

Applicant's institution:

Peking University Cancer Hospital & Institute

研究负责人所在单位:

北京肿瘤医院(北京大学肿瘤医院)

Affiliation of the Leader:

Beijing Cancer Hospital

是否获伦理委员会批准:

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

2025KT03

伦理委员会批件附件:

Approved file of Ethical Committee:

查看附件View

批准本研究的伦理委员会名称:

北京肿瘤医院医学伦理委员会

Name of the ethic committee:

Institutional Review Board of Beijing Cancer Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-01-08 00:00:00

伦理委员会联系人:

廖红舞

Contact Name of the ethic committee:

Liao HongWu

伦理委员会联系地址:

北京海淀区阜成路52号

Contact Address of the ethic committee:

52 Fucheng Road Haidian District Beijing

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 8819 6391

伦理委员会联系人邮箱:

Contact email of the ethic committee:

liaohongwu2015@163.com

研究实施负责(组长)单位:

北京肿瘤医院(北京大学肿瘤医院)

Primary sponsor:

Beijing Cancer Hospital

研究实施负责(组长)单位地址:

北京海淀区阜成路52号

Primary sponsor's address:

52 Fucheng Road Haidian District Beijing

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

北京市

市(区县):

Country:

China

Province:

Beijing

City:

单位(医院):

北京肿瘤医院(北京大学肿瘤医院)

具体地址:

北京海淀区阜成路52号

Institution
hospital:

Beijing Cancer Hospital

Address:

52 Fucheng Road Haidian District Beijing

经费或物资来源:

临床医学发展专项“扬帆”计划

Source(s) of funding:

Beijing Hospitals Authority Clinical medicine Development of special funding support

研究疾病:

胃镜病理确诊为胃腺癌患者  

Target disease:

Patients diagnosed with gastric adenocarcinoma

研究疾病代码:

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

本课题的核心目标是解决胃癌TN分期及新辅助治疗疗效预测中的关键问题,并在现有的影像学与人工智能技术基础上进行方法学上的创新与优化。通过引入迁移学习技术,利用预训练模型对高质控影像数据进行微调,显著提升了模型的泛化能力和稳定性,既能充分利用已有的大规模临床影像数据,减少训练时间,又提高了对胃癌TN分期诊断的准确性。同时,本研究通过多模态数据的融合,结合分割、分类等多任务模型,使得新辅助治疗的疗效评估更加精准和全面。模型的应用场景和实际临床效果作为验证的核心点,旨在突破当前临床上诊断准确度不足、疗效评估不准的技术瓶颈,为胃癌患者的治疗方案制定提供更强的辅助支持。  

Objectives of Study:

The objective of this study is to address key challenges in TN staging of gastric cancer and prediction of neoadjuvant therapy efficacy, while introducing methodological innovations and optimizations based on existing imaging and artificial intelligence technologies. By incorporating transfer learning techniques and fine-tuning pre-trained models with high-quality controlled imaging data, the model’s generalization ability and stability are significantly enhanced. This approach not only leverages large-scale clinical imaging datasets and reduces training time, but also improves the accuracy of TN staging diagnosis in gastric cancer. Furthermore, through the integration of multimodal data and the use of multitask models combining segmentation and classification, the evaluation of neoadjuvant therapy efficacy becomes more precise and comprehensive. Validation of the model in real-world clinical scenarios serves as a core focus, aiming to overcome current limitations in diagnostic accuracy and treatment response assessment, thereby providing stronger decision-making support for treatment planning in gastric cancer patients.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

Inclusion criteria

排除标准:

1.淋巴结清扫数目不足15枚;
2.缺少临床信息及随访信息;

Exclusion criteria:

1.Fewer than 15 lymph nodes dissected;
2.Lacking clinical information and follow-up data;

研究实施时间:

Study execute time:

From 2025-01-01 00:00:00 To 2027-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-11-20 00:00:00 To 2027-12-31 00:00:00

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

术后病理

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

Postoperative pathological results

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

基于病灶自动识别与自动分割技术的胃癌人工智能影像辅助诊断系统

Index test:

An Artificial Intelligence–Based Imaging-Assisted Diagnostic System for Gastric Cancer Using Automatic Lesion Detection and Segmentation Technology

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

胃癌患者

例数:

Sample size:

130

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

patients with gastric adenocarcinoma

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

不是腺癌的胃癌患者

例数:

Sample size:

0

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

Patients with gastric cancer other than adenocarcinoma

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

北京肿瘤医院(北京大学肿瘤医院) 

单位级别:

三级甲等 

Institution
hospital:

Beijing Cancer Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

北京大学第三医院 

单位级别:

三级甲等 

Institution
hospital:

Peking University Third Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

中国医学科学院肿瘤医院 

单位级别:

三级甲等 

Institution
hospital:

Cancer Hospital Chinese Academy of Medical Sciences

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

辽宁省 

市(区县):

 

Country:

China

Province:

Liaoning

City:

单位(医院):

辽宁省肿瘤医院(辽宁省肿瘤研究所) 

单位级别:

三级甲等 

Institution
hospital:

Liaoning Cancer Hospital & Institute

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

首都医科大学附属北京友谊医院 

单位级别:

三级甲等 

Institution
hospital:

Beijing Friendship Hospital ,Capital Medical University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

北京大学人民医院 

单位级别:

三级甲等 

Institution
hospital:

Peking University People's Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

灵敏度

指标类型:

主要指标

Outcome:

Sensitivity

Type:

Primary indicator

测量时间点:

基线诊断以及新辅助治疗行评效CT后

测量方法:

专家组读片、试验组基于病灶自动识别与分割及多模型集成等诊断模型和评效模型进行读片

Measure time point of outcome:

At baseline diagnosis and after efficacy assessment CT following neoadjuvant therapy

Measure method:

In the expert group, image interpretation is performed by specialists, while in the experimental group, interpretation is conducted using diagnostic and efficacy-assessment models based on automatic lesion detection and segmentation, as well as multi-model ensemble techniques.

指标中文名:

准确度

指标类型:

主要指标

Outcome:

Accuracy

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异度

指标类型:

次要指标

Outcome:

Specificity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

NA

Tissue:

人体标本去向

其它  

说明

Fate of sample:

0thers  

Note:

征募研究对象情况:

Recruiting status:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 90 years

性别:

男女均可

Gender:

Both

随机方法(请说明由何人用什么方法产生随机序列):

Randomization Procedure (please state who generates the random number sequence and by what method):

None

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

不公开/Private

盲法:

Blinding:

None

是否共享原始数据:

IPD sharing

否No

共享原始数据的方式(说明:请填入公开原始数据日期和方式,如采用网络平台,需填该网络平台名称和网址):

none

The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url):

none

数据采集和管理(说明:数据采集和管理由两部分组成,一为病例记录表(Case Record Form, CRF),二为电子采集和管理系统(Electronic Data Capture, EDC),如ResMan即为一种基于互联网的EDC:

数据采集和管理有两部分组成,一为病例记录表,二为excel表管理数据

Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture:

Data collection and management consist of two components: case report forms and Excel-based data management.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-11-11 15:35:09